From 2e3a9cba3527b1e9da014d21c4680b349640e4eb Mon Sep 17 00:00:00 2001
From: 4am <a2_4am@sent.com>
Date: Fri, 3 Dec 2021 16:42:47 -0500
Subject: [PATCH] split out shr.80boxes.common

---
 src/fx/fx.shr.80boxes.a        | 478 +--------------------------------
 src/fx/fx.shr.80boxes.common.a | 232 ++++++++++++++++
 2 files changed, 242 insertions(+), 468 deletions(-)
 create mode 100644 src/fx/fx.shr.80boxes.common.a

diff --git a/src/fx/fx.shr.80boxes.a b/src/fx/fx.shr.80boxes.a
index 0c38d4a04..311505b8c 100644
--- a/src/fx/fx.shr.80boxes.a
+++ b/src/fx/fx.shr.80boxes.a
@@ -6,154 +6,8 @@
 !to "build/FX.INDEXED/SHR.80BOXES",plain
 *=$A000
 
-; The SHR screen in 320x200 mode is separated into 80 boxes.
-; Boxes are laid out in a grid, left-to-right, top-down:
-;
-; 0  1  2  3  4  5  6  7  8  9
-; 10 11 12 13 14 15 16 17 18 19
-; 20 21 22 23 24 25 26 27 28 29
-; 30 31 32 33 34 35 36 37 38 39
-; 40 41 42 43 44 45 46 47 48 49
-; 50 51 52 53 54 55 56 57 58 59
-; 60 61 62 63 64 65 66 67 68 69
-; 70 71 72 73 74 75 76 77 78 79
-;
-; Each box is 32x25 pixels, so each row of each box is 16 consecutive
-; bytes in memory (2 pixels per byte) once you calculate the SHR base
-; address for that row.
-;
-; |BoxStages| defines the initial grid of stages for each box.
-; Each stage is used as an index into the |StagesHi| array
-; to find the drawing routine for that stage (if any).
-; Each box's stage is incremented after each iteration through the main loop.
-; When the main loop iterates through all 80 boxes without drawing anything,
-; the program exits.
-;
-; There are 7 clear routines that set certain pixels to color 0 (usually black)
-; labeled clear00..clear06. clear00 clears the inner-most box, and
-; clear06 clears the outermost box (see diagram).
-; There are 7 copy routines that copy certain pixels from the source
-; image in mainmem to the destination image in auxmem, labeled copy00..copy06.
-;
-; row|             pixels
-; ---+.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
-; 00 |66666666666666666666666666666666
-; 01 |66666666666666666666666666666666
-; 02 |66555555555555555555555555555566
-; 03 |66555555555555555555555555555566
-; 04 |66554444444444444444444444445566
-; 05 |66554444444444444444444444445566
-; 06 |66554433333333333333333333445566
-; 07 |66554433333333333333333333445566
-; 08 |66554433222222222222222233445566
-; 09 |66554433222222222222222233445566
-; 10 |66554433221111111111112233445566
-; 11 |66554433221111111111112233445566
-; 12 |66554433221100000000112233445566
-; 13 |66554433221111111111112233445566
-; 14 |66554433221111111111112233445566
-; 15 |66554433222222222222222233445566
-; 16 |66554433222222222222222233445566
-; 17 |66554433333333333333333333445566
-; 18 |66554433333333333333333333445566
-; 19 |66554444444444444444444444445566
-; 20 |66554444444444444444444444445566
-; 21 |66555555555555555555555555555566
-; 22 |66555555555555555555555555555566
-; 23 |66666666666666666666666666666666
-; 24 |66666666666666666666666666666666
-;
-; Each routine manipulates pixels in horizontal pairs, meaning we can copy
-; bytes without having to worry about masking high and low nibbles.
-; Each routine except copy00 is similar, defined by 4 parameters:
-; - top row (absolute row, i.e. 00..C7)
-; - bottom row (should probably use the first of the two, also absolute)
-; - left (should probably be in bytes, also absolute)
-; - right (should probably be in bytes, also absolute)
-;
-; On [top row] and [top row + 1], copy bytes from [left offset] to [right offset]
-; While [current row] < [bottom row], draw 1 byte at [left offset] and 1 byte at [right offset]
-; On [bottom row] and [bottom row + 1], copy bytes from [left offset] to [right offset]
+         !source "src/fx/fx.shr.80boxes.common.a"
 
-shrlo     = $201                     ; [$C8 bytes]
-shrhi     = $301                     ; [$C8 bytes]
-
-         !source "src/fx/macros.a"
-         !source "src/fx/fx.shr.common.a"
-
-         ldx   #0
--        ldy   start, x
-         sty   $00, x
-         sta   EndStagesHi, x
-         inx
-         bne   -
-
-         stx   seta+1
-         stx   sub1+1
-         ldx   #-25
-         stx   sub2+1
----      ldx   #8
-seta     lda   #0
---       pha
-         ldy   #10-1
--        sta   (<src), y
-         sec
-sub1     sbc   #0
-         dey
-         bpl   -
-         clc
-         lda   <src
-         adc   #10
-         sta   <src
-         pla
-         sec
-sub2     sbc   #-25
-         dex
-         bne   --
-         lda   #$90
-         sta   seta+1
-         lda   #$10
-         sta   sub1+1
-         stx   sub2+1
-         bcc   ---
-
-         +BUILD_SHR_LOOKUP_TABLES shrlo, shrhi
-         +COPY_SCB_AND_PALETTES
-         ;WRITEAUXMEM active
-
-         jmp   MainLoop
-
-start
-!pseudopc 0 {
-MainLoop ldx   #80
-BoxLoop  ldy   <BoxStages-1, x       ; for each box, get its current stage
-         inc   <BoxStages-1, x       ; increment every box's stage every time through the loop
-         lda   StagesHi, y
-         beq   NextBox               ; if stage's drawing routine is 0, nothing to do
-         sta   <j+2
-         lda   BoxesX-1, x           ; A = starting SHR row for this box
-         ldy   BoxesY-1, x           ; Y = starting byte offset for this box
-         clc
-         stx   <ReBox+1
-j        jsr   $0000                 ; [SMC] call drawing routine for this stage
-ReBox    ldx   #$00                  ; [SMC]
-NextBox  dex
-         bne   <BoxLoop
-         lda   <j+2
-         beq   <exit                 ; if we didn't draw anything in any box, we're done
-         stx   <j+2                  ; X=0 here
-         bit   $C000
-         bpl   MainLoop
-exit     sta   WRITEMAINMEM
-setV     rts
-
-src      !word BoxesX
-rowcount !byte 0
-lefty    !byte 0
-righty   !byte 0
-
-; diagonal - VERY GOOD
-BoxStages
          !byte $F9,$F8,$F7,$F6,$F5,$F4,$F3,$F2,$F1,$F0
          !byte $FA,$F9,$F8,$F7,$F6,$F5,$F4,$F3,$F2,$F1
          !byte $FB,$FA,$F9,$F8,$F7,$F6,$F5,$F4,$F3,$F2
@@ -163,324 +17,12 @@ BoxStages
          !byte $FF,$FE,$FD,$FC,$FB,$FA,$F9,$F8,$F7,$F6
          !byte $00,$FF,$FE,$FD,$FC,$FB,$FA,$F9,$F8,$F7
 
-; diagonal
-;BoxStages
-;         !byte $F2,$F0,$EE,$EC,$EA,$E8,$E6,$E4,$E2,$E0
-;         !byte $F4,$F2,$F0,$EE,$EC,$EA,$E8,$E6,$E4,$E2
-;         !byte $F6,$F4,$F2,$F0,$EE,$EC,$EA,$E8,$E6,$E4
-;         !byte $F8,$F6,$F4,$F2,$F0,$EE,$EC,$EA,$E8,$E6
-;         !byte $FA,$F8,$F6,$F4,$F2,$F0,$EE,$EC,$EA,$E8
-;         !byte $FC,$FA,$F8,$F6,$F4,$F2,$F0,$EE,$EC,$EA
-;         !byte $FE,$FC,$FA,$F8,$F6,$F4,$F2,$F0,$EE,$EC
-;         !byte $00,$FE,$FC,$FA,$F8,$F6,$F4,$F2,$F0,$EE
-
-; spiral
-;BoxStages
-;         !byte $E9,$E8,$E7,$E6,$E5,$E4,$E3,$E2,$E1,$00
-;         !byte $EA,$CF,$CE,$CD,$CC,$CB,$CA,$C9,$E0,$FF
-;         !byte $EB,$D0,$BD,$BC,$BB,$BA,$B9,$C8,$DF,$FE
-;         !byte $EC,$D1,$BE,$B3,$B2,$B1,$B8,$C7,$DE,$FD
-;         !byte $ED,$D2,$BF,$B4,$B5,$B6,$B7,$C6,$DD,$FC
-;         !byte $EE,$D3,$C0,$C1,$C2,$C3,$C4,$C5,$DC,$FB
-;         !byte $EF,$D4,$D5,$D6,$D7,$D8,$D9,$DA,$DB,$FA
-;         !byte $F0,$F1,$F2,$F3,$F4,$F5,$F6,$F7,$F8,$F9
-
-; snake
-;BoxStages
-;         !byte $00,$FF,$FE,$FD,$FC,$FB,$FA,$F9,$F8,$F7
-;         !byte $ED,$EE,$EF,$F0,$F1,$F2,$F3,$F4,$F5,$F6
-;         !byte $EC,$EB,$EA,$E9,$E8,$E7,$E6,$E5,$E4,$E3
-;         !byte $D9,$DA,$DB,$DC,$DD,$DE,$DF,$E0,$E1,$E2
-;         !byte $D8,$D7,$D6,$D5,$D4,$D3,$D2,$D1,$D0,$CF
-;         !byte $C5,$C6,$C7,$C8,$C9,$CA,$CB,$CC,$CD,$CE
-;         !byte $C4,$C3,$C2,$C1,$C0,$BF,$BE,$BD,$BC,$BB
-;         !byte $B1,$B2,$B3,$B4,$B5,$B6,$B7,$B8,$B9,$BA
-
-; snake 2
-;BoxStages
-;         !byte $00,$00,$FF,$FF,$FE,$FE,$FD,$FD,$FC,$FC
-;         !byte $F7,$F7,$F8,$F8,$F9,$F9,$FA,$FA,$FB,$FB
-;         !byte $F6,$F6,$F5,$F5,$F4,$F4,$F3,$F3,$F2,$F2
-;         !byte $ED,$ED,$EE,$EE,$EF,$EF,$F0,$F0,$F1,$F1
-;         !byte $EC,$EC,$EB,$EB,$EA,$EA,$E9,$E9,$E8,$E8
-;         !byte $E3,$E3,$E4,$E4,$E5,$E5,$E6,$E6,$E7,$E7
-;         !byte $E2,$E2,$E1,$E1,$E0,$E0,$DF,$DF,$DE,$DE
-;         !byte $D9,$D9,$DA,$DA,$DB,$DB,$DC,$DC,$DD,$DD
-
-; l2r alternating - VERY GOOD
-;BoxStages
-;         !byte $00,$FE,$FC,$FA,$F8,$F6,$F4,$F2,$F0,$EE
-;         !byte $ED,$EF,$F1,$F3,$F5,$F7,$F9,$FB,$FD,$FF
-;         !byte $00,$FE,$FC,$FA,$F8,$F6,$F4,$F2,$F0,$EE
-;         !byte $ED,$EF,$F1,$F3,$F5,$F7,$F9,$FB,$FD,$FF
-;         !byte $00,$FE,$FC,$FA,$F8,$F6,$F4,$F2,$F0,$EE
-;         !byte $ED,$EF,$F1,$F3,$F5,$F7,$F9,$FB,$FD,$FF
-;         !byte $00,$FE,$FC,$FA,$F8,$F6,$F4,$F2,$F0,$EE
-;         !byte $ED,$EF,$F1,$F3,$F5,$F7,$F9,$FB,$FD,$FF
-
-; l2r alternating 2
-;BoxStages
-;         !byte $00,$FF,$FE,$FD,$FC,$FB,$FA,$F9,$F8,$F7
-;         !byte $F7,$F8,$F9,$FA,$FB,$FC,$FD,$FE,$FF,$00
-;         !byte $00,$FF,$FE,$FD,$FC,$FB,$FA,$F9,$F8,$F7
-;         !byte $F7,$F8,$F9,$FA,$FB,$FC,$FD,$FE,$FF,$00
-;         !byte $00,$FF,$FE,$FD,$FC,$FB,$FA,$F9,$F8,$F7
-;         !byte $F7,$F8,$F9,$FA,$FB,$FC,$FD,$FE,$FF,$00
-;         !byte $00,$FF,$FE,$FD,$FC,$FB,$FA,$F9,$F8,$F7
-;         !byte $F7,$F8,$F9,$FA,$FB,$FC,$FD,$FE,$FF,$00
-
-; u2d alternating
-;BoxStages
-;         !byte $00,$F1,$00,$F1,$00,$F1,$00,$F1,$00,$F1
-;         !byte $FE,$F3,$FE,$F3,$FE,$F3,$FE,$F3,$FE,$F3
-;         !byte $FC,$F5,$FC,$F5,$FC,$F5,$FC,$F5,$FC,$F5
-;         !byte $FA,$F7,$FA,$F7,$FA,$F7,$FA,$F7,$FA,$F7
-;         !byte $F8,$F9,$F8,$F9,$F8,$F9,$F8,$F9,$F8,$F9
-;         !byte $F6,$FB,$F6,$FB,$F6,$FB,$F6,$FB,$F6,$FB
-;         !byte $F4,$FD,$F4,$FD,$F4,$FD,$F4,$FD,$F4,$FD
-;         !byte $F2,$FF,$F2,$FF,$F2,$FF,$F2,$FF,$F2,$FF
-}
-
-!macro INIT_DRAW .toprowoffset, .siderowcount, .leftoffset {
-         adc   #.toprowoffset
-         ldx   #.siderowcount
-         stx   rowcount
-         tax
-         tya
-         adc   #.leftoffset
-         sta   lefty
-}
-
-!macro SET_ROW_X {
-         lda   shrlo, x
-         sta   <src
-         lda   shrhi, x
-         sta   <src+1
-         ldy   lefty
-}
-
-!macro COPY_BYTE {
-         lda   (src), y
-         sta   (src), y
-}
-
-!macro COPY_BYTE_AND_INY {
-         +COPY_BYTE
-         iny
-}
-
-!macro SIDE_ROWS {
-@siderows
-         sty   righty
-         +SET_ROW_X
-         +COPY_BYTE
-         ldy   righty
-         +COPY_BYTE
-         inx
-         dec   rowcount
-         bne   @siderows
-}
-
-!align $FF,0,0                       ; align to page
-copy00
-         +INIT_DRAW 12, 0, 6
-         +SET_ROW_X
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE
-         rts
-
-BoxesX ; starting row for each box
-;         !byte 0,0,0,0,0,0,0,0,0,0
-;         !byte 25,25,25,25,25,25,25,25,25,25
-;         !byte 50,50,50,50,50,50,50,50,50,50
-;         !byte 75,75,75,75,75,75,75,75,75,75
-;         !byte 100,100,100,100,100,100,100,100,100,100
-;         !byte 125,125,125,125,125,125,125,125,125,125
-;         !byte 150,150,150,150,150,150,150,150,150,150
-;         !byte 175,175,175,175,175,175,175,175,175,175
-BoxesY = BoxesX + 10*8 ; starting byte offset for each box
-;         !byte $00,$10,$20,$30,$40,$50,$60,$70,$80,$90
-;         !byte $00,$10,$20,$30,$40,$50,$60,$70,$80,$90
-;         !byte $00,$10,$20,$30,$40,$50,$60,$70,$80,$90
-;         !byte $00,$10,$20,$30,$40,$50,$60,$70,$80,$90
-;         !byte $00,$10,$20,$30,$40,$50,$60,$70,$80,$90
-;         !byte $00,$10,$20,$30,$40,$50,$60,$70,$80,$90
-;         !byte $00,$10,$20,$30,$40,$50,$60,$70,$80,$90
-;         !byte $00,$10,$20,$30,$40,$50,$60,$70,$80,$90
-!if (>BoxesY != >BoxesX) {
-  !error "Boxes array crosses a page"
-}
-
-!align $FF,0,0                       ; align to page
-copy01
-         +INIT_DRAW 10, 1, 5
-         bit   <setV
---       clc
-         !byte $A9
--        sec
-         +SET_ROW_X
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE
-         inx
-         bcc   -
-         bvc   +
-         +SIDE_ROWS
-         clv
-         jmp   --
-+        rts
-
-!align $FF,0,0                       ; align to page
-copy02
-         +INIT_DRAW 8, 5, 4
-         bit   <setV
---       clc
-         !byte $A9
--        sec
-         +SET_ROW_X
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE
-         inx
-         bcc   -
-         bvc   +
-         +SIDE_ROWS
-         clv
-         jmp   --
-+        rts
-
-!align $FF,0,0                       ; align to page
-copy03
-         +INIT_DRAW 6, 9, 3
-         bit   <setV
---       clc
-         !byte $A9
--        sec
-         +SET_ROW_X
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE
-         inx
-         bcc   -
-         bvc   +
-         +SIDE_ROWS
-         clv
-         jmp   --
-+        rts
-
-!align $FF,0,0                       ; align to page
-copy04
-         +INIT_DRAW 4, 13, 2
-         bit   <setV
---       clc
-         !byte $A9
--        sec
-         +SET_ROW_X
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE
-         inx
-         bcc   -
-         bvc   +
-         +SIDE_ROWS
-         clv
-         jmp   --
-+        rts
-
-!align $FF,0,0                       ; align to page
-copy05
-         +INIT_DRAW 2, 17, 1
-         bit   <setV
---       clc
-         !byte $A9
--        sec
-         +SET_ROW_X
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE
-         inx
-         bcc   -
-         bvc   +
-         +SIDE_ROWS
-         clv
-         jmp   --
-+        rts
-
-!align $FF,0,0                       ; align to page
-copy06
-         +INIT_DRAW 0, 21, 0
-         bit   <setV
---       clc
-         !byte $A9
--        sec
-         +SET_ROW_X
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE_AND_INY
-         +COPY_BYTE
-         inx
-         bcc   -
-         bvc   +
-         +SIDE_ROWS
-         clv
-         jmp   --
-+        rts
-
-StagesHi ; high bytes of address of drawing routine for each stage
-         !byte >copy00
-         !byte >copy01
-         !byte >copy02
-         !byte >copy03
-         !byte >copy04
-         !byte >copy05
-         !byte >copy06
-EndStagesHi
+StageInitialIndexes
+         !byte 1
+         !byte 2
+         !byte 3
+         !byte 4
+         !byte 5
+         !byte 6
+         !byte 7
+EndStageInitialIndexes
diff --git a/src/fx/fx.shr.80boxes.common.a b/src/fx/fx.shr.80boxes.common.a
new file mode 100644
index 000000000..19edd293d
--- /dev/null
+++ b/src/fx/fx.shr.80boxes.common.a
@@ -0,0 +1,232 @@
+;license:MIT
+;(c) 2021 by 4am & qkumba
+;
+; The SHR screen in 320x200 mode is separated into 80 boxes.
+; Boxes are laid out in a grid, left-to-right, top-down:
+;
+; 0  1  2  3  4  5  6  7  8  9
+; 10 11 12 13 14 15 16 17 18 19
+; 20 21 22 23 24 25 26 27 28 29
+; 30 31 32 33 34 35 36 37 38 39
+; 40 41 42 43 44 45 46 47 48 49
+; 50 51 52 53 54 55 56 57 58 59
+; 60 61 62 63 64 65 66 67 68 69
+; 70 71 72 73 74 75 76 77 78 79
+;
+; Each box is 32x25 pixels, so each row of each box is 16 consecutive
+; bytes in memory (2 pixels per byte) once you calculate the SHR base
+; address for that row.
+;
+; |BoxInitialStages| defines the initial grid of stages for each box.
+; Each stage is used as an index into the |StageInitialIndexes| array
+; to find the drawing routine for that stage (if any).
+; Each box's stage is incremented after each iteration through the main loop.
+; When the main loop iterates through all 80 boxes without drawing anything,
+; the program exits.
+;
+; There are 7 copy routines that copy certain pixels from the source
+; image in mainmem to the destination image in auxmem. Technically
+; these all have the same entry point, with X = 1..7 on entry.
+; We always copy pixels in horizontal pairs, meaning we can just copy
+; bytes without having to worry about masking high and low nibbles.
+;
+; row|             pixels
+; ---+.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
+; 00 |77777777777777777777777777777777
+; 01 |77777777777777777777777777777777
+; 02 |77666666666666666666666666666677
+; 03 |77666666666666666666666666666677
+; 04 |77665555555555555555555555556677
+; 05 |77665555555555555555555555556677
+; 06 |77665544444444444444444444556677
+; 07 |77665544444444444444444444556677
+; 08 |77665544333333333333333344556677
+; 09 |77665544333333333333333344556677
+; 10 |77665544332222222222223344556677
+; 11 |77665544332222222222223344556677
+; 12 |77665544332211111111223344556677
+; 13 |77665544332222222222223344556677
+; 14 |77665544332222222222223344556677
+; 15 |77665544333333333333333344556677
+; 16 |77665544333333333333333344556677
+; 17 |77665544444444444444444444556677
+; 18 |77665544444444444444444444556677
+; 19 |77665555555555555555555555556677
+; 20 |77665555555555555555555555556677
+; 21 |77666666666666666666666666666677
+; 22 |77666666666666666666666666666677
+; 23 |77777777777777777777777777777777
+; 24 |77777777777777777777777777777777
+;
+
+!macro SET_ROW_X {
+; out:   Z=0 because shrhi is never 0
+         lda   shrlo, x
+         sta   <src+1
+         lda   shrhi, x
+         sta   <src+2
+}
+
+!macro COPY_BYTE {
+         lda   (src+1), y
+         sta   (src+1), y
+}
+
+!macro COPY_BYTE_AND_INY {
+         +COPY_BYTE
+         iny
+}
+
+!macro SIDE_ROWS {
+}
+
+shrlo     = $201                     ; [$C8 bytes][accessed via shrlo-1][should not cross page]
+shrhi     = $301                     ; [$C8 bytes][accessed via shrhi-1][should not cross page]
+BoxStages = $106                     ; [$50 bytes][should not cross page]
+StageIndexes = $BD00                 ; [$100 bytes][should be page-aligned]
+BoxesX    = $BE60                    ; [$50 bytes][accessed via BoxesX-1][should not cross page]
+BoxesY    = $BEB0                    ; [$50 bytes][accessed via BoxesY-1][should not cross page]
+
+         !source "src/fx/macros.a"   ; no code in these
+         !source "src/fx/fx.shr.common.a"
+
+         ldx   #80
+         lda   #175
+--       ldy   #10
+-        sta   BoxesX-1, x
+         dex
+         dey
+         bne   -
+         sec
+         sbc   #25
+         bcs   --
+         ldx   #80
+--       ldy   #10
+         lda   #$90
+-        sta   BoxesY-1, x
+         sec
+         sbc   #$10
+         dex
+         dey
+         bne   -
+         txa
+         bne   --
+-        lda   start, x
+         sta   <MainLoop, x
+         lda   #0
+         sta   EndStageInitialIndexes, x
+         lda   StageInitialIndexes, x
+         sta   StageIndexes, x
+         inx
+         bne   -
+         ldx   #80                   ; can't do full $100 here because we'd clobber the stack
+-        lda   BoxInitialStages-1, x
+         sta   BoxStages-1, x
+         dex
+         bne   -
+         +BUILD_SHR_LOOKUP_TABLES shrlo, shrhi
+         +COPY_SCB_AND_PALETTES
+         ;WRITEAUXMEM active
+         jmp   MainLoop
+
+start
+!pseudopc 0 {
+MainLoop ldx   #80
+BoxLoop  ldy   BoxStages-1, x        ; for each box, get its current stage
+         inc   BoxStages-1, x        ; increment every box's stage every time through the loop
+         lda   StageIndexes, y
+         beq   NextBox               ; if stage's index is 0, nothing to do
+         sta   <StageIndex+1
+         stx   <ReBox+1
+         lda   BoxesX-1, x           ; A = starting SHR row for this box
+         ldy   BoxesY-1, x           ; Y = starting byte offset for this box
+         clc
+StageIndex
+         ldx   #$00                  ; [SMC] X = stage index 1..7
+         jsr   copy
+ReBox    ldx   #$00                  ; [SMC] X = BoxLoop index 1..80
+NextBox  dex
+         bne   BoxLoop
+         lda   <StageIndex+1
+         beq   <exit                 ; if we didn't draw anything in any box, we're done
+         stx   <StageIndex+1         ; X=0 here
+         bit   $C000
+         bpl   MainLoop
+exit     sta   WRITEMAINMEM
+setV     rts
+
+toprow   !byte 12,10,8,6,4,2,0
+leftbyte !byte 6,5,4,3,2,1
+siderows !byte 0,1,5,9,13,17,21
+across_lo
+         !byte <across1
+         !byte <across2
+         !byte <across3
+         !byte <across4
+         !byte <across5
+         !byte <across6
+
+across6  +COPY_BYTE_AND_INY
+         +COPY_BYTE_AND_INY
+across5  +COPY_BYTE_AND_INY
+         +COPY_BYTE_AND_INY
+across4  +COPY_BYTE_AND_INY
+         +COPY_BYTE_AND_INY
+across3  +COPY_BYTE_AND_INY
+         +COPY_BYTE_AND_INY
+across2  +COPY_BYTE_AND_INY
+         +COPY_BYTE_AND_INY
+across1  +COPY_BYTE_AND_INY
+         +COPY_BYTE_AND_INY
+across0  +COPY_BYTE_AND_INY
+         +COPY_BYTE_AND_INY
+         +COPY_BYTE_AND_INY
+         lda   (src+1), y
+src      sta   $FDFD, y              ; [SMC]
+copyexit rts
+copy1    pla
+         tax
+         ldy   <lefty+1
+         +SET_ROW_X
+         bne   across0               ; always branches
+copy     adc   toprow-1, x
+         pha
+         tya
+         adc   leftbyte-1, x
+         sta   <lefty+1
+         lda   siderows-1, x
+         sta   <rowcount
+         dex
+         beq   copy1
+         lda   across_lo-1, x
+         sta   <j+1
+         pla
+         tax
+         bit   <setV
+copy2row clc
+         !byte $A9
+copy1row sec
+         +SET_ROW_X
+         ldy   <lefty+1
+j        jsr   across6               ; [SMC low byte]
+         inx
+         bcc   copy1row
+         bvc   copyexit
+         sty   <righty+1
+copyside +SET_ROW_X
+lefty    ldy   #$FD                  ; [SMC]
+         +COPY_BYTE
+righty   ldy   #$FD                  ; [SMC]
+         +COPY_BYTE
+         inx
+         dec   <rowcount
+         bne   copyside
+         clv
+         bvc   copy2row
+rowcount
+}
+!if (*-start>=$FF) {
+         !error "Code is too big to fit on zero page! ", *-start
+}
+
+BoxInitialStages